On Wed, Aug 27, 2014 at 04:38:04PM -0500, Felipe Balbi wrote:
> Commit 71c731a (usb: host: xhci: Fix Compliance Mode
> on SN65LVP3502CP Hardware) implemented a workaround
> for a known issue with Texas Instruments' USB 3.0
> redriver IC but it left a condition where any xHCI
> host would be taken out of reset if port was placed
> in compliance mode and there was no device connected
> to the port.
>
> That condition would trigger a fake connection to a
> non-existent device so that usbcore would trigger a
> warm reset of the port, thus taking the link out of
> reset.
>
> This has the side-effect of preventing any xHCI host
> connected to a Linux machine from starting and running
> the USB 3.0 Electrical Compliance Suite because the
> port will mysteriously taken out of compliance mode
> and, thus, xHCI won't step through the necessary
> compliance patterns for link validation.
>
> This patch fixes the issue by just adding a missing
> check for XHCI_COMP_MODE_QUIRK inside
> xhci_hub_report_usb3_link_state() when PORT_CAS isn't
> set.
>
> This patch should be backported to all kernels containing
> commit 71c731a.
>
> Fixes: 71c731a (usb: host: xhci: Fix Compliance Mode on SN65LVP3502CP Hardware)
> Cc: Alexis R. Cortes <alexis.cortes@xxxxxx>
> Cc: <stable@xxxxxxxxxxxxxxx> # v3.2+
> Signed-off-by: Felipe Balbi <balbi@xxxxxx>
> ---
>
> This has been tested on a certification setup with LeCroy Voyager M3i
> and a really expensive oscilloscope :-)
>
> Without this patch we cannot keep the host in compliance.
>
> drivers/usb/host/xhci-hub.c | 8 +++++---
> 1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
> index aa79e87..69aece3 100644
> --- a/drivers/usb/host/xhci-hub.c
> +++ b/drivers/usb/host/xhci-hub.c
> @@ -468,7 +468,8 @@ static void xhci_hub_report_usb2_link_state(u32 *status, u32 status_reg)
> }
>
> /* Updates Link Status for super Speed port */
> -static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg)
> +static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
> + u32 *status, u32 status_reg)
> {
> u32 pls = status_reg & PORT_PLS_MASK;
>
> @@ -507,7 +508,8 @@ static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg)
> * in which sometimes the port enters compliance mode
> * caused by a delay on the host-device negotiation.
> */
> - if (pls == USB_SS_PORT_LS_COMP_MOD)
> + if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) &&
> + (pls == USB_SS_PORT_LS_COMP_MOD))
> pls |= USB_PORT_STAT_CONNECTION;
> }
>
> @@ -666,7 +668,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
> }
> /* Update Port Link State */
> if (hcd->speed == HCD_USB3) {
> - xhci_hub_report_usb3_link_state(&status, raw_port_status);
> + xhci_hub_report_usb3_link_state(xhci, &status, raw_port_status);
> /*
> * Verify if all USB3 Ports Have entered U0 already.
> * Delete Compliance Mode Timer if so.
Looks good, Mathias, can I get an ACK so I can queue this up now?
thanks,
greg k-h
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html